def test_bedslice():
chromsizes = util.read_chromsizes(op.join(datadir, 'toy.chrom.sizes'))
bins = util.binnify(chromsizes, 10)
grouped = bins.groupby('chrom')
df = util.bedslice(grouped, chromsizes, 'chr1:0-12')
assert df['chrom'].tolist() == ['chr1', 'chr1']
assert df['start'].tolist() == [0, 10]
def test_parse_region():
chromsizes = util.read_chromsizes(op.join(datadir, 'toy.chrom.sizes'))
assert util.parse_region(('chr1', 0, 10)) == ('chr1', 0, 10)
assert util.parse_region('chr1:0-10') == ('chr1', 0, 10)
assert util.parse_region('chr1:0-',
chromsizes) == ('chr1', 0, chromsizes['chr1'])
# Don't accept undefined end unless chromsizes exists
# NOTE: parse_region_string works here
with pytest.raises(ValueError):
util.parse_region('chr1:0-')
# catch end < start in non-string case
with pytest.raises(ValueError):
util.parse_region(('chr1', 10, 0))
# catch errors when chromsizes is given
for region in [
('chr1', 0, 1000),
('chr1', -5, 10),
('DoesNotExist', 0, 10),
'DoesNotExist',
]:
with pytest.raises(ValueError):
util.parse_region(region, chromsizes)
def prepare_snakemake(allc_table_path, output_dir, chrom_sizes_path, template_path, chroms=None, smoothing=True,
chunk_size=50000000):
output_dir = pathlib.Path(output_dir).absolute()
output_dir.mkdir(exist_ok=True)
allc_table = pd.read_csv(allc_table_path, sep='\t')
allc_table.columns = ['allc_path', 'sample', 'group']
if allc_table['group'].unique().size != 2:
raise ValueError(
f"There must be two and only two different groups, got {allc_table['group'].unique().size}."
)
group1, group2 = allc_table['group'].unique()
group1_allc = allc_table.loc[allc_table['group'] == group1,
'allc_path'].tolist()
group2_allc = allc_table.loc[allc_table['group'] == group2,
'allc_path'].tolist()
group1_id = allc_table.loc[allc_table['group'] == group1, 'sample'].tolist()
group2_id = allc_table.loc[allc_table['group'] == group2, 'sample'].tolist()
chrom_sizes = read_chromsizes(chrom_sizes_path).reindex(chroms)
if chroms is None:
chroms = chrom_sizes.index.tolist()
bins = binnify(chrom_sizes.loc[chroms], binsize=chunk_size)
regions = []
for _, (chrom, start, end) in bins.iterrows():
region = f'{chrom}:{start}-{end}'
regions.append(region)
for region in regions:
config_path = f'{output_dir}/{region}.yaml'
parameters = dict(region=region,
allc_paths=group1_allc + group2_allc,
group1=group1_id,
group2=group2_id,
smoothing=smoothing)
with open(config_path, 'w') as f:
f.write(yaml.dump(parameters))
snakefile = f"""
regions = {regions}
rule main:
input:
expand('{{region}}.DSS.DML.hdf', region=regions)
rule papermill:
input:
nb='{template_path}',
config='{{region}}.yaml'
output:
nb='{{region}}.ipynb',
data='{{region}}.DSS.DML.hdf'
shell:
'papermill {{input.nb}} {{output.nb}} -f {{input.config}} && sleep 10'
"""
snakefile_path = f'{output_dir}/Snakefile'
with open(snakefile_path, 'w') as f:
f.write(snakefile)
return snakefile_path
def test_genome_segmentation():
chromsizes = util.read_chromsizes(op.join(datadir, 'toy.chrom.sizes'))
bins = util.binnify(chromsizes, 10)
gs = util.GenomeSegmentation(chromsizes, bins)
df = gs.fetch('chr1')
assert len(df) == 4
df = gs.fetch('chr1:2-30')
assert len(df) == 3
util.balanced_partition(gs, 2, ['chr1'])
def test_get_binsize():
chromsizes = util.read_chromsizes(op.join(datadir, 'toy.chrom.sizes'))
bins = util.binnify(chromsizes, 10)
assert util.get_binsize(bins) == 10
# variable-sized bins
bins = pd.read_csv(op.join(datadir, 'toy.bins.var.bed'),
names=['chrom', 'start', 'end'],
sep='\t')
assert util.get_binsize(bins) is None
# ambiguous case: one bin per chromosome with different lengths
bins = pd.DataFrame({
'chrom': ['chr1', 'chr2', 'chr3'],
'start': [0, 0, 0],
'end': [100, 200, 300]
})
assert util.get_binsize(bins) is None
def prepare_snakemake(allc_table_path,
output_dir,
chrom_sizes_path,
template_path,
chroms=None,
test_covariate='group',
match_covariate=None,
adjust_covariate=None,
cutoff=0.1,
min_num_region=3,
smooth=True,
bp_span=1000,
min_in_span=30,
max_gap_smooth=2500,
max_gap=1000,
verbose=True,
max_perms=10,
stat="stat",
block=False,
block_size=5000,
chrs_per_chunk=1,
cpu=40,
chunk_size=5000000000):
output_dir = pathlib.Path(output_dir).absolute()
output_dir.mkdir(exist_ok=True)
chrom_sizes = read_chromsizes(chrom_sizes_path).reindex(chroms)
if chroms is None:
chroms = chrom_sizes.index.tolist()
bins = binnify(chrom_sizes.loc[chroms], binsize=chunk_size)
regions = []
for _, (chrom, start, end) in bins.iterrows():
region = f'{chrom}:{start}-{end}'
regions.append(region)
for region in regions:
config_path = f'{output_dir}/{region}.yaml'
parameters = {
'region': region,
'allc_table_path': allc_table_path,
'test_covariate': test_covariate,
'match_covariate': match_covariate,
'adjust_covariate': adjust_covariate,
'cutoff': cutoff,
'min_num_region': min_num_region,
'smooth': smooth,
'bp_span': bp_span,
'min_in_span': min_in_span,
'max_gap_smooth': max_gap_smooth,
'max_gap': max_gap,
'verbose': verbose,
'max_perms': max_perms,
'stat': stat,
'block': block,
'block_size': block_size,
'chrs_per_chunk': chrs_per_chunk,
'cpu': cpu
}
with open(config_path, 'w') as f:
f.write(yaml.dump(parameters))
snakefile = f"""
regions = {regions}
rule main:
input:
expand('{{region}}.DMR.hdf', region=regions)
rule papermill:
input:
nb='{template_path}',
config='{{region}}.yaml'
output:
nb='{{region}}.ipynb',
data='{{region}}.DMR.hdf'
threads:
1 #{cpu}
shell:
'papermill {{input.nb}} {{output.nb}} -f {{input.config}} && sleep 10'
"""
snakefile_path = f'{output_dir}/Snakefile'
with open(snakefile_path, 'w') as f:
f.write(snakefile)
return regions
def test_check_bins():
chromsizes = util.read_chromsizes(op.join(datadir, 'toy.chrom.sizes'))
bins = util.binnify(chromsizes, 10)
bins['chrom'] = bins['chrom'].astype(str)
bins = util.check_bins(bins, chromsizes)
assert pd.api.types.is_categorical(bins["chrom"])
def test_get_chromsizes():
chromsizes = util.read_chromsizes(op.join(datadir, 'toy.chrom.sizes'))
bins = util.binnify(chromsizes, 10)
assert np.allclose(util.get_chromsizes(bins), chromsizes)
def test_binnify():
chromsizes = util.read_chromsizes(op.join(datadir, 'toy.chrom.sizes'))
bins = util.binnify(chromsizes, 10)
assert len(bins) == 8
def test_read_chromsizes():
util.read_chromsizes(op.join(datadir, 'toy.chrom.sizes'))
